| { | |
| "best_metric": 0.42575815320014954, | |
| "best_model_checkpoint": "speecht5_finetuned_bphc/checkpoint-500", | |
| "epoch": 2.6595744680851063, | |
| "eval_steps": 100, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13297872340425532, | |
| "grad_norm": 3.7797725200653076, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.0695, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.26595744680851063, | |
| "grad_norm": 4.549177169799805, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.7576, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39893617021276595, | |
| "grad_norm": 4.847335338592529, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.6571, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "grad_norm": 8.47089958190918, | |
| "learning_rate": 9.7e-05, | |
| "loss": 0.624, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "eval_loss": 0.5379713177680969, | |
| "eval_runtime": 18.8881, | |
| "eval_samples_per_second": 35.419, | |
| "eval_steps_per_second": 17.736, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6648936170212766, | |
| "grad_norm": 3.0278241634368896, | |
| "learning_rate": 9.449999999999999e-05, | |
| "loss": 0.595, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7978723404255319, | |
| "grad_norm": 4.422701358795166, | |
| "learning_rate": 8.825e-05, | |
| "loss": 0.5809, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9308510638297872, | |
| "grad_norm": 4.076521396636963, | |
| "learning_rate": 8.2e-05, | |
| "loss": 0.5634, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "grad_norm": 5.123497009277344, | |
| "learning_rate": 7.575e-05, | |
| "loss": 0.5563, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "eval_loss": 0.5066816210746765, | |
| "eval_runtime": 18.5524, | |
| "eval_samples_per_second": 36.06, | |
| "eval_steps_per_second": 18.057, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.196808510638298, | |
| "grad_norm": 17.09893226623535, | |
| "learning_rate": 6.95e-05, | |
| "loss": 0.5311, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.3297872340425532, | |
| "grad_norm": 2.976322889328003, | |
| "learning_rate": 6.324999999999999e-05, | |
| "loss": 0.5287, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.4627659574468086, | |
| "grad_norm": 2.6360063552856445, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 0.5182, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "grad_norm": 2.318189859390259, | |
| "learning_rate": 5.075e-05, | |
| "loss": 0.5121, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "eval_loss": 0.46897533535957336, | |
| "eval_runtime": 18.3638, | |
| "eval_samples_per_second": 36.43, | |
| "eval_steps_per_second": 18.242, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.728723404255319, | |
| "grad_norm": 4.144455909729004, | |
| "learning_rate": 4.4500000000000004e-05, | |
| "loss": 0.5006, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.8617021276595744, | |
| "grad_norm": 3.1114983558654785, | |
| "learning_rate": 3.825e-05, | |
| "loss": 0.493, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.9946808510638299, | |
| "grad_norm": 4.484862804412842, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.4862, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "grad_norm": 7.771288871765137, | |
| "learning_rate": 2.5750000000000002e-05, | |
| "loss": 0.4795, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "eval_loss": 0.4404144883155823, | |
| "eval_runtime": 18.5295, | |
| "eval_samples_per_second": 36.105, | |
| "eval_steps_per_second": 18.079, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.2606382978723403, | |
| "grad_norm": 3.972978115081787, | |
| "learning_rate": 1.9500000000000003e-05, | |
| "loss": 0.478, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.393617021276596, | |
| "grad_norm": 4.415282726287842, | |
| "learning_rate": 1.3250000000000002e-05, | |
| "loss": 0.4722, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.526595744680851, | |
| "grad_norm": 3.901869773864746, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 0.4623, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.6595744680851063, | |
| "grad_norm": 6.222782135009766, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.4622, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.6595744680851063, | |
| "eval_loss": 0.42575815320014954, | |
| "eval_runtime": 18.6784, | |
| "eval_samples_per_second": 35.817, | |
| "eval_steps_per_second": 17.935, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1478228411981376.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |